© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1868
    Prev
    Next
    INDEX
    Explanations

    best option

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTime
    0.42
    需
    0.41
    绘制
    0.40
    Hasil
    0.40
    朢
    0.40
    補助
    0.39
    变量
    0.39
    只要
    0.38
    Undefined
    0.38
    攻擊
    0.38
    POSITIVE LOGITS
     Luxurious
    0.42
    ઓએ
    0.42
     Stories
    0.40
    들도
    0.39
     Species
    0.39
     Smoothie
    0.39
     Musicians
    0.39
     Serbian
    0.39
     illustrious
    0.38
    lerimiz
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.